- Notifications
You must be signed in to change notification settings - Fork1.6k
Pull requests: NVIDIA/TensorRT-LLM
Author
Uh oh!
There was an error while loading.Please reload this page.
Label
Uh oh!
There was an error while loading.Please reload this page.
Projects
Uh oh!
There was an error while loading.Please reload this page.
Milestones
Uh oh!
There was an error while loading.Please reload this page.
Reviews
Assignee
Assigned to nobodyLoading
Uh oh!
There was an error while loading.Please reload this page.
Sort
Pull requests list
[https://nvbugs/5361178][fix]: Json schema support in trtllm-serve using xgrammar Community want to contributePRs initiated from Community
#6197 openedJul 18, 2025 bymayani-nvLoading…
enh: Lift expectation of single image per sample in Gemma3 VLM
#6195 openedJul 18, 2025 bybrb-nvLoading…
fix: Allreduce Strategy is not correctly set for MNNVL fallback.
#6194 openedJul 18, 2025 bytimlee0212Loading…
fix: Ensure mlx5 library is installed for deep_ep and remove deprecated python bindings
#6189 openedJul 18, 2025 byMartinMarciniszynLoading…
fix: Ensure that Python stub generation works against libnvidia-ml stubs
#6188 openedJul 18, 2025 byMartinMarciniszynLoading…
[fix] Correct the returned value of has_spec_drafter
#6178 openedJul 18, 2025 byziyixiong-nvLoading…
[fix] Fix can_use_alltoall in fused_moe_wide_ep.py
#6173 openedJul 18, 2025 byjinyangyuan-nvidiaLoading…
[Perf]: Add residual, norm and AR fusions for llama and nemotron_nas models
#6157 openedJul 17, 2025 byNVShreyasLoading…
[feat] Enable TP and batching for PixtralVisionModel / Mistral3VLM
#6152 openedJul 17, 2025 by2ez4bzLoading…
doc: remove cuda_graph_config: {} from doc since cuda_graph enabled b…
#6150 openedJul 17, 2025 bynv-guomingzLoading…
[fix]: Skip prompt length checking for generation only requests
#6146 openedJul 17, 2025 byLinPolyLoading…
[TRTLLM-6537][infra] extend multi-gpu tests related file list
#6139 openedJul 17, 2025 byreasonsoloLoading…
[nvbug/5322354] fix PD + MTP + overlap scheduler accuracy issue
#6136 openedJul 17, 2025 byyweng0828Loading…
[TRTLLM-6549] chore: record delay introduced by disaggregated serving in kv cache measure
#6135 openedJul 17, 2025 byzhengd-nvLoading…
ProTip! Addingno:label will show everything without a label.